Image pre-processing and shadow detection for building extraction from high-resolution satellite images

Dolonchapa Prabhakar; Pradeep Kumar Garg

doi:10.1117/12.2678670

19 October 2023 Image pre-processing and shadow detection for building extraction from high-resolution satellite images

Dolonchapa Prabhakar, Pradeep Kumar Garg

Proceedings Volume 12735, Remote Sensing Technologies and Applications in Urban Environments VIII; 1273508 (2023) https://doi.org/10.1117/12.2678670
Event: SPIE Remote Sensing, 2023, Amsterdam, Netherlands

Abstract

High resolution satellite imageries frequently contain shadows because of high-rise structures, especially in urban areas. One of the notable flaws in remotely sensed imaging that prevents information extraction is shadow. Building detection depends on the recognition of shadowy areas since they indicate a building's presence. Therefore, we can determine the structures' shapes and heights by utilizing the sun's illumination direction. But more crucially, detecting building shadows in high-resolution images can aid in better building detection. This work presents a shadow detection approach from a single RGB image to reduce the shadow effects on high-resolution images. We used LAB color space, which has one luminance (L) channel and two-color channels (A and B). To generate the buffer zone for building extraction, we transformed the RGB images to the CIELab color space to acquire the shadow masks. The proposed algorithm must be pre-processed to separate each shadow area into a separate data matrix to expand its functionality, evaluate the effectiveness of the method, and produce more accurate results when building shadows are close to one another. Additionally, by grouping the shadow zones into independent matrices, the method enables the detection of two or more distinct shadows of buildings with complex geometries and many parts in separate zones. Pre-processing helps us to prepare the images for further analysis. Using image pre-processing wisely, one can offer advantages and address issues that ultimately improve local and global feature detection. The effectiveness of building extraction and the outcomes of image analysis both dramatically improved results by image pre-processing.

Conference Presentation

(2023) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Dolonchapa Prabhakar and Pradeep Kumar Garg "Image pre-processing and shadow detection for building extraction from high-resolution satellite images", Proc. SPIE 12735, Remote Sensing Technologies and Applications in Urban Environments VIII, 1273508 (19 October 2023); https://doi.org/10.1117/12.2678670

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available